© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13686
    Prev
    Next
    INDEX
    Explanations

    mentions of different individuals within a particular context

    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
    453
    +0.17
    0.5%
    964
    +0.12
    0.4%
    50
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.06
    1001
    +0.12
    0.05
    724
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.09
     magnify
    -0.56
     thoughtless
    -0.55
     or
    -0.55
     and
    -0.53
    тол
    -0.51
     to
    -0.51
     bestow
    -0.51
     endeavouring
    -0.51
     unwarran
    -0.51
    POSITIVE LOGITS
     alkoh
    1.45
     kosme
    1.27
     kompati
    1.27
     antik
    1.27
     silikon
    1.27
     kram
    1.25
     optik
    1.23
     akut
    1.22
     praktik
    1.21
     logis
    1.20
    Activations Density 0.106%

    No Known Activations