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. 13983
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions or assessments

    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
    1804
    +0.10
    0.3%
    872
    +0.09
    0.2%
    569
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.10
    0.06
    1287
    +0.09
    0.04
    919
    +0.08
    0.03
    Negative Logits
     kram
    -1.43
     alkoh
    -1.36
     plak
    -1.27
     „,
    -1.27
     solidar
    -1.26
     meis
    -1.25
     makro
    -1.25
     stoff
    -1.22
     gesta
    -1.22
     ohr
    -1.20
    POSITIVE LOGITS
     of
    1.22
     của
    0.91
    of
    0.88
     Of
    0.85
    Of
    0.82
    ของ
    0.82
     thereof
    0.74
     της
    0.64
     של
    0.62
     ของ
    0.61
    Activations Density 0.322%

    No Known Activations