© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    statements or discussions related to learning and education

    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
    30
    +0.15
    0.5%
    554
    +0.14
    0.5%
    1510
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.15
    0.05
    554
    +0.14
    0.05
    1512
    +0.10
    0.04
    Negative Logits
    Allister
    -0.69
     pamph
    -0.66
    Namara
    -0.65
    Cormack
    -0.63
     Mejía
    -0.58
    Leod
    -0.57
    Millan
    -0.57
    Grath
    -0.57
     courtier
    -0.57
    Dermott
    -0.55
    POSITIVE LOGITS
     learn
    1.20
     LEARN
    1.18
    learn
    1.15
    LEARN
    1.10
     learned
    1.09
     Learn
    1.09
    Lear
    1.06
    Learn
    1.06
     learning
    1.05
     learns
    1.04
    Activations Density 0.073%

    No Known Activations