© 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. 3393
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format "month year"

    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
    1013
    +0.11
    0.3%
    776
    +0.10
    0.3%
    1978
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1429
    +0.11
    0.04
    321
    +0.10
    0.04
    648
    +0.09
    0.03
    Negative Logits
     smtplib
    -0.59
    bouncycastle
    -0.59
    .*")]
    -0.58
     dichi
    -0.56
     ricorda
    -0.56
     abbra
    -0.52
     \%$\\
    -0.52
    ]');
    -0.52
    }}$\\
    -0.51
     pymongo
    -0.51
    POSITIVE LOGITS
     onwards
    0.65
     until
    0.61
     till
    0.61
    until
    0.60
    Until
    0.56
     untill
    0.54
     onward
    0.54
     lupo
    0.51
     Until
    0.51
     bosco
    0.50
    Activations Density 0.086%

    No Known Activations