© 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. 1079
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations, specifically related to coastal areas

    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
    1810
    +0.13
    0.5%
    1806
    +0.13
    0.5%
    204
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.13
    0.02
    1810
    +0.13
    0.02
    662
    +0.12
    0.02
    Negative Logits
     maneu
    -0.88
     shenan
    -0.88
     encomp
    -0.87
     reluct
    -0.86
     inol
    -0.84
     disagre
    -0.82
     unve
    -0.81
     increa
    -0.81
     Confe
    -0.80
     impra
    -0.79
    POSITIVE LOGITS
     coast
    1.39
     Coast
    1.31
     COAST
    1.17
    coast
    1.17
    Coast
    1.14
     coastal
    1.01
     coasts
    0.98
     coastline
    0.96
     Coastal
    0.94
    coastal
    0.85
    Activations Density 0.085%

    No Known Activations