© 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. 7233
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or decisions

    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
    1177
    +0.13
    0.4%
    690
    +0.11
    0.3%
    1244
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.13
    0.07
    1244
    +0.11
    0.05
    100
    +0.10
    0.06
    Negative Logits
    GLenum
    -0.52
    ve
    -0.52
    ﷺ
    -0.48
    itemize
    -0.48
     dolar
    -0.48
    cja
    -0.48
    FECHA
    -0.48
    here
    -0.47
    IC
    -0.47
    lll
    -0.47
    POSITIVE LOGITS
     depic
    1.42
     reluct
    1.37
     aquarelle
    1.35
     inext
    1.34
     maneu
    1.32
     hentai
    1.32
     apprehen
    1.31
     excru
    1.31
     emphat
    1.30
     gaily
    1.30
    Activations Density 0.655%

    No Known Activations