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. 8259
    Prev
    Next
    INDEX
    Explanations

    cases or scenarios where a problem arises

    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
    1150
    +0.10
    0.3%
    674
    +0.10
    0.3%
    1108
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.10
    0.02
    1026
    +0.10
    0.02
    1548
    +0.09
    0.02
    Negative Logits
     palio
    -0.86
     riva
    -0.80
     virtù
    -0.77
     archivio
    -0.76
     sopr
    -0.76
     quegli
    -0.75
     pietre
    -0.74
     Luglio
    -0.73
     autunno
    -0.72
     ridu
    -0.72
    POSITIVE LOGITS
     unspeak
    0.68
     ineffec
    0.66
     unavoid
    0.65
     vainly
    0.64
     apprehen
    0.63
     rouse
    0.63
     gratify
    0.61
     crouching
    0.59
     prolly
    0.58
     case
    0.57
    Activations Density 0.133%

    No Known Activations