© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, settings, and directions

    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
    62
    +0.10
    0.3%
    190
    +0.09
    0.2%
    1319
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.06
    2044
    +0.09
    0.06
    510
    +0.08
    0.05
    Negative Logits
     dises
    -1.20
     accla
    -1.16
     sappi
    -1.14
     Keny
    -1.11
     peculi
    -1.08
     volunte
    -1.08
     emphat
    -1.07
     Cik
    -1.06
     parteci
    -1.06
     inev
    -1.06
    POSITIVE LOGITS
    <bos>
    0.93
     we
    0.80
     please
    0.76
     wohin
    0.72
    ,
    0.71
     you
    0.68
     zumal
    0.66
     weshalb
    0.65
    的话
    0.65
     consider
    0.64
    Activations Density 0.385%

    No Known Activations