© 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. 7595
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing guidance or instructions, especially in a formal or informative context

    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
    1325
    +0.15
    0.6%
    1892
    +0.13
    0.5%
    920
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.02
    1892
    +0.13
    0.02
    1325
    +0.13
    0.02
    Negative Logits
    Demografía
    -0.50
    FlatAppearance
    -0.49
    ayaquil
    -0.48
     Darm
    -0.47
     Glä
    -0.45
    ghijklmnop
    -0.45
    
    
    -0.45
    ghijkl
    -0.44
    imarães
    -0.43
    sibirsk
    -0.42
    POSITIVE LOGITS
     guide
    1.31
    guide
    1.24
     guides
    1.24
     Guide
    1.17
     Guides
    1.13
    Guide
    1.12
     GUIDE
    1.10
    Guides
    1.08
     guiding
    1.04
    guides
    1.03
    Activations Density 0.080%

    No Known Activations