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. 13142
    Prev
    Next
    INDEX
    Explanations

    mentions of various towns and communities

    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
    1350
    +0.10
    0.4%
    650
    +0.10
    0.4%
    1971
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.10
    0.02
    1336
    +0.10
    0.03
    650
    +0.09
    0.02
    Negative Logits
     île
    -0.50
     vogel
    -0.50
     fucks
    -0.50
     fucker
    -0.49
     irritate
    -0.49
     shiver
    -0.47
     disreg
    -0.47
     letti
    -0.46
     agence
    -0.46
     zima
    -0.45
    POSITIVE LOGITS
     town
    1.29
    Town
    1.19
     Town
    1.14
     towns
    1.12
     TOWN
    1.09
    town
    0.98
    towns
    0.92
    Towns
    0.89
    TOWN
    0.87
     Towns
    0.85
    Activations Density 0.076%

    No Known Activations