© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 642
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, film, and arts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    812
    +0.09
    0.3%
    943
    +0.06
    0.2%
    1311
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    943
    +0.06
    0.02
    99
    +0.06
    0.02
    Negative Logits
    /*
    -0.69
    
    
    -0.64
    <?
    -0.64
    ⓧ
    -0.55
    toBeDefined
    -0.54
    /**
    -0.54
     she
    -0.53
     have
    -0.53
    #
    -0.52
     so
    -0.52
    POSITIVE LOGITS
    its
    1.87
    ITS
    1.51
     eyel
    1.17
     milano
    1.16
     stockholm
    1.15
     maroc
    1.15
     scrat
    1.12
     venuto
    1.12
     affor
    1.07
     erec
    1.06
    Activations Density 0.144%

    No Known Activations