© 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. 1096
    Prev
    Next
    INDEX
    Explanations

    mentions of neighborhood or community issues

    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
    544
    +0.13
    0.5%
    78
    +0.13
    0.5%
    1137
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.13
    0.03
    544
    +0.13
    0.03
    1137
    +0.12
    0.03
    Negative Logits
     saluti
    -0.65
     letti
    -0.61
     commerci
    -0.57
     soggior
    -0.55
    Scopri
    -0.54
     FEBR
    -0.54
    Доброго
    -0.52
     paes
    -0.52
     CONCEP
    -0.52
     imprend
    -0.51
    POSITIVE LOGITS
     residents
    1.24
     resident
    1.23
     Residents
    1.17
    resident
    1.14
    Residents
    1.13
     Resident
    1.13
    residents
    1.13
    Resident
    1.13
     residency
    0.95
     residence
    0.93
    Activations Density 0.056%

    No Known Activations