© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations related to growing plants and metrics

    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
    1482
    +0.13
    0.5%
    1325
    +0.11
    0.4%
    538
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.05
    538
    +0.11
    0.04
    1705
    +0.10
    0.05
    Negative Logits
    abases
    -0.70
    haden
    -0.51
    AsUp
    -0.51
    atterns
    -0.51
    enumii
    -0.49
    ostoma
    -0.49
    romolecules
    -0.49
    InjectAttribute
    -0.49
    Referencie
    -0.48
    romole
    -0.47
    POSITIVE LOGITS
     intersper
    0.87
     reluct
    0.84
     quitted
    0.82
     bandung
    0.80
     depic
    0.76
    Tic
    0.76
    «<
    0.76
     Augu
    0.75
     naer
    0.75
     whofe
    0.72
    Activations Density 0.317%

    No Known Activations