Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13618
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and programming

    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
    876
    +0.19
    0.6%
    1042
    +0.15
    0.4%
    1403
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.19
    -0.01
    284
    +0.15
    0.04
    1403
    +0.11
    0.01
    Negative Logits
    <bos>
    -0.95
     Michoacán
    -0.76
     doña
    -0.75
     campesinos
    -0.71
     Almería
    -0.70
     Cataluña
    -0.70
     Atenas
    -0.69
    expandindo
    -0.69
    assertAll
    -0.67
    Trimethyl
    -0.67
    POSITIVE LOGITS
     maneu
    1.64
     shenan
    1.56
     encomp
    1.53
     impra
    1.51
     reluct
    1.44
     increa
    1.43
     guarante
    1.42
     hairc
    1.40
     attemp
    1.39
     affor
    1.38
    Activations Density 0.368%

    No Known Activations