© 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. 14305
    Prev
    Next
    INDEX
    Explanations

    numerical data points and technical terms related to surveillance and security

    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
    184
    +0.14
    0.4%
    1343
    +0.14
    0.4%
    1013
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.04
    1013
    +0.14
    0.05
    1531
    +0.11
    0.04
    Negative Logits
     wien
    -2.20
     effe
    -2.15
     doman
    -2.05
     „,
    -2.02
     mef
    -1.98
     fta
    -1.98
     aen
    -1.94
     dispen
    -1.91
     inder
    -1.90
     ivi
    -1.89
    POSITIVE LOGITS
     and
    0.97
     и
    0.83
     or
    0.83
     và
    0.80
     et
    0.79
     everywhere
    0.78
    和
    0.78
     for
    0.78
     etc
    0.77
    และ
    0.75
    Activations Density 0.296%

    No Known Activations