© 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. 7625
    Prev
    Next
    INDEX
    Explanations

    instructions related to coding steps and commands

    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
    876
    +0.25
    0.8%
    856
    +0.12
    0.4%
    1510
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.25
    -0.00
    872
    +0.12
    0.03
    764
    +0.11
    0.02
    Negative Logits
    <bos>
    -0.69
     Milán
    -0.67
     Öster
    -0.66
     Joko
    -0.65
     Catedral
    -0.64
     feria
    -0.63
     Asunción
    -0.63
     Siria
    -0.62
     Naciones
    -0.62
     Jokowi
    -0.62
    POSITIVE LOGITS
     scrat
    1.43
     tupperware
    1.42
     affor
    1.38
     guarante
    1.31
     increa
    1.31
     purcha
    1.29
     peppa
    1.28
     perfet
    1.28
     philips
    1.27
     oreo
    1.24
    Activations Density 0.092%

    No Known Activations