© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    information related to academic and professional backgrounds of individuals

    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
    227
    +0.18
    0.5%
    283
    +0.10
    0.3%
    1343
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.05
    1574
    +0.10
    0.02
    974
    +0.10
    0.03
    Negative Logits
    }-${
    -0.55
    OrFail
    -0.55
    !("{
    -0.53
     입니다
    -0.52
     besz
    -0.51
     loamy
    -0.50
     kerül
    -0.49
    ]();
    -0.49
    putable
    -0.49
    ())));
    -0.49
    POSITIVE LOGITS
     Præ
    1.05
     Souha
    1.00
     „,
    0.99
     Chá
    0.98
     §.
    0.98
     Khart
    0.96
     Græ
    0.96
     emphat
    0.96
     doman
    0.95
     Traité
    0.94
    Activations Density 0.144%

    No Known Activations