© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 755
    Prev
    Next
    INDEX
    Explanations

    phrases related to advancements, development, or achievements

    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
    50
    +0.09
    0.3%
    2011
    +0.07
    0.3%
    1334
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.09
    0.03
    1048
    +0.07
    0.03
    1242
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.33
    public
    -0.69
    void
    -0.63
    ɵɵ
    -0.62
    /**
    -0.60
    ⓧ
    -0.60
     also
    -0.59
    @
    -0.59
     springfox
    -0.59
    echo
    -0.58
    POSITIVE LOGITS
     progress
    1.90
     Progress
    1.81
     Progression
    1.77
     affor
    1.74
     progression
    1.74
    progress
    1.73
     bandung
    1.70
     stockholm
    1.69
     jaya
    1.68
     PROGRESS
    1.68
    Activations Density 0.083%

    No Known Activations