© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10653
    Prev
    Next
    INDEX
    Explanations

    references to attacks and conflicts related to various social, political, and military contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    752
    +0.11
    0.3%
    1085
    +0.10
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.11
    0.04
    2016
    +0.10
    0.04
    31
    +0.10
    0.03
    Negative Logits
     complejidad
    -0.57
    enteuer
    -0.54
     âges
    -0.54
     Betracht
    -0.53
     mxArray
    -0.51
     Decke
    -0.51
    AndEndTag
    -0.48
     folgendes
    -0.47
    inguishing
    -0.47
    PLACEMENT
    -0.46
    POSITIVE LOGITS
     Simult
    1.00
     Cfr
    0.98
     Juf
    0.93
     Perci
    0.92
     haer
    0.86
     Olof
    0.86
     Bartholo
    0.85
     Godt
    0.84
     Prova
    0.84
     sergio
    0.84
    Activations Density 0.226%

    No Known Activations