© 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 EvalsExportsAPI 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. 5417
    Prev
    Next
    INDEX
    Explanations

    parentheses and numerical values separated by forward slashes

    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
    1678
    +0.10
    0.3%
    1150
    +0.10
    0.3%
    2034
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1678
    +0.10
    0.04
    941
    +0.10
    0.04
    871
    +0.09
    0.04
    Negative Logits
    OGND
    -0.75
    ThroughAttribute
    -0.75
     ideolog
    -0.72
    onViewCreated
    -0.71
     affez
    -0.67
     tortas
    -0.66
     venuto
    -0.65
    onAttach
    -0.64
     esboço
    -0.63
     abstra
    -0.61
    POSITIVE LOGITS
     unspeak
    1.51
     shenan
    1.45
     reluct
    1.33
     disagre
    1.27
     impra
    1.27
     indescri
    1.25
     sophistic
    1.24
     apprehen
    1.23
     caucasian
    1.21
     disreg
    1.20
    Activations Density 0.196%

    No Known Activations