© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13029
    Prev
    Next
    INDEX
    Explanations

    phrases related to data processing and analysis

    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
    453
    +0.09
    0.3%
    1135
    +0.08
    0.2%
    1993
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1201
    +0.09
    0.03
    2010
    +0.08
    0.03
    1379
    +0.08
    0.03
    Negative Logits
     Áng
    -0.70
     mView
    -0.52
     Cerca
    -0.50
     createdBy
    -0.50
     curé
    -0.49
     joindre
    -0.48
     Siga
    -0.48
     cristianismo
    -0.48
     getPost
    -0.47
     getNome
    -0.47
    POSITIVE LOGITS
     kram
    0.91
     Verk
    0.71
     zir
    0.70
     tyn
    0.69
     zyn
    0.67
     Klagen
    0.67
     kasa
    0.65
     elek
    0.65
     kac
    0.65
     makro
    0.64
    Activations Density 0.187%

    No Known Activations