© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12972
    Prev
    Next
    INDEX
    Explanations

    references related to legal and financial matters

    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
    599
    +0.17
    0.5%
    1150
    +0.13
    0.4%
    612
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.17
    0.08
    1224
    +0.13
    0.08
    1870
    +0.11
    0.04
    Negative Logits
    __;
    -0.53
    randomUUID
    -0.48
    **/
    
    -0.48
     Reak
    -0.48
    الإنجليزية
    -0.47
     Dosis
    -0.46
    ്ട
    -0.46
     Röntgen
    -0.46
    </u>
    -0.46
     du
    -0.46
    POSITIVE LOGITS
     disagre
    1.45
     unspeak
    1.41
     unwarran
    1.38
     indescri
    1.32
     indestru
    1.32
     hairc
    1.27
     excru
    1.26
     shenan
    1.23
     reluct
    1.22
     tolerably
    1.18
    Activations Density 0.841%

    No Known Activations