© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    times and locations expressed as numbers

    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
    1978
    +0.16
    0.5%
    1013
    +0.14
    0.4%
    776
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.16
    0.05
    776
    +0.14
    0.05
    609
    +0.12
    0.04
    Negative Logits
    <bos>
    -0.73
    strona
    -0.66
    собенности
    -0.66
    Trotz
    -0.63
    Natürlich
    -0.63
    Mə
    -0.62
    Dazu
    -0.62
    Портали
    -0.61
    Bereits
    -0.61
    Dieses
    -0.60
    POSITIVE LOGITS
     inev
    1.27
     encomp
    1.23
     accla
    1.21
     depic
    1.20
     maneu
    1.18
     reluct
    1.15
     increa
    1.11
     disagre
    1.11
     impra
    1.10
     attemp
    1.09
    Activations Density 0.139%

    No Known Activations