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. 15025
    Prev
    Next
    INDEX
    Explanations

    technical information related to software or product updates

    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
    964
    +0.23
    0.8%
    1343
    +0.23
    0.8%
    845
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.23
    0.04
    1784
    +0.23
    0.03
    845
    +0.13
    0.02
    Negative Logits
     betweenstory
    -0.63
     Palest
    -0.54
    fastjson
    -0.52
    Brainz
    -0.52
     frau
    -0.49
     skak
    -0.48
     sved
    -0.47
    Karakteristik
    -0.46
     bronz
    -0.45
    Unset
    -0.45
    POSITIVE LOGITS
     encomp
    0.73
     hairc
    0.65
    sightly
    0.61
     quoique
    0.60
     swarovski
    0.60
     lmfao
    0.57
     shewn
    0.56
     createDate
    0.56
     useNavigate
    0.56
     biex
    0.56
    Activations Density 0.184%

    No Known Activations