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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2219
    Prev
    Next
    INDEX
    Explanations

    short phrases describing actions or events

    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
    674
    +0.16
    0.5%
    1177
    +0.15
    0.5%
    184
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.16
    0.04
    184
    +0.15
    0.02
    1842
    +0.14
    0.03
    Negative Logits
    .
    -0.63
    ...
    -0.57
    ↵↵
    -0.56
    ().
    -0.56
    </
    -0.55
    。
    -0.54
    !
    -0.54
    _
    -0.54
    ..
    -0.54
    (
    -0.53
    POSITIVE LOGITS
     Juf
    1.38
     intersper
    1.37
     ftu
    1.27
     apprehen
    1.26
     fta
    1.25
     hentai
    1.23
     alberto
    1.22
     Augu
    1.21
     emphat
    1.21
     encomp
    1.20
    Activations Density 0.160%

    No Known Activations