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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12897
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    1334
    +0.15
    0.6%
    239
    +0.12
    0.5%
    577
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.07
    577
    +0.12
    0.05
    370
    +0.11
    0.05
    Negative Logits
     šte
    -0.63
     tež
    -0.59
     pono
    -0.53
     occorre
    -0.52
     podjet
    -0.51
    iranje
    -0.50
     življen
    -0.50
     sarebbero
    -0.49
     druge
    -0.48
     manj
    -0.48
    POSITIVE LOGITS
     dav
    0.78
     Lav
    0.77
    av
    0.77
    Lav
    0.76
     Dav
    0.75
    ev
    0.74
    Dav
    0.74
     Av
    0.73
     Pav
    0.73
    Pav
    0.73
    Activations Density 0.460%

    No Known Activations