Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7859
    Prev
    Next
    INDEX
    Explanations

    mentions of performance-related terms and details, possibly related to technological research or achievements

    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
    1870
    +0.16
    0.6%
    528
    +0.13
    0.5%
    1778
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.16
    0.02
    1618
    +0.13
    0.02
    528
    +0.12
    0.02
    Negative Logits
     indestru
    -0.85
     embra
    -0.84
     Messieurs
    -0.78
     Mlle
    -0.74
     Darío
    -0.69
     sappi
    -0.68
     Pantal
    -0.67
     Souha
    -0.67
     disting
    -0.67
     ardu
    -0.66
    POSITIVE LOGITS
     performance
    1.31
     Performance
    1.21
    performance
    1.21
    Performance
    1.15
     PERFORMANCE
    1.07
     performances
    1.05
    PERFORMANCE
    1.00
     performers
    0.81
     perform
    0.80
     Performances
    0.80
    Activations Density 0.064%

    No Known Activations