© 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. 16305
    Prev
    Next
    INDEX
    Explanations

    terms related to configuring and sending log data using specific parameters and functions

    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
    1150
    +0.18
    0.6%
    1343
    +0.16
    0.5%
    394
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1871
    +0.18
    0.04
    876
    +0.16
    -0.00
    394
    +0.15
    0.03
    Negative Logits
    modelos
    -0.66
    detalles
    -0.65
    ejercicio
    -0.63
     much
    -0.61
    paquete
    -0.60
    Сю
    -0.60
     big
    -0.59
    Див
    -0.58
    তথ্য
    -0.58
     United
    -0.57
    POSITIVE LOGITS
     !...
    1.92
     ?...
    1.79
     igno
    1.75
     effe
    1.72
     seiz
    1.66
     fto
    1.61
     illi
    1.60
     embra
    1.58
     :)))
    1.58
     unil
    1.57
    Activations Density 0.153%

    No Known Activations