© 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. 3545
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development processes and requirements

    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
    1385
    +0.10
    0.3%
    876
    +0.09
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1297
    +0.10
    0.01
    814
    +0.09
    0.01
    1383
    +0.09
    0.03
    Negative Logits
     andato
    -0.66
     Sì
    -0.65
     venuto
    -0.64
     Cfr
    -0.64
     sappi
    -0.59
     Molto
    -0.59
     €)
    -0.59
     diventato
    -0.58
     riuscito
    -0.57
     arrivato
    -0.55
    POSITIVE LOGITS
     across
    0.83
     throughout
    0.81
    across
    0.80
     everywhere
    0.79
     regardless
    0.76
     Across
    0.69
     ACROSS
    0.68
     uniform
    0.67
    throughout
    0.67
    Across
    0.66
    Activations Density 0.437%

    No Known Activations