© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    content related to financial terms and investor responsibilities

    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
    1042
    +0.13
    0.4%
    453
    +0.12
    0.4%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.13
    0.03
    185
    +0.12
    0.02
    44
    +0.10
    0.01
    Negative Logits
     murmuring
    -1.08
     intersper
    -1.02
     unspeak
    -0.99
     intrigu
    -0.99
     exagger
    -0.94
     horrend
    -0.94
     stifled
    -0.93
     adjour
    -0.92
     savag
    -0.92
     encomp
    -0.92
    POSITIVE LOGITS
     lampa
    0.96
     fede
    0.95
     piaci
    0.93
     frans
    0.93
     torba
    0.92
     confé
    0.89
     alkoh
    0.89
     affez
    0.88
     silikon
    0.88
     preghiera
    0.87
    Activations Density 0.170%

    No Known Activations