© 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. 139
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "shore"

    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
    1937
    +0.08
    0.2%
    197
    +0.07
    0.2%
    554
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1928
    +0.08
    0.02
    485
    +0.07
    0.02
    292
    +0.07
    0.02
    Negative Logits
    WriteLiteral
    -0.79
    int
    -0.76
    beforeEach
    -0.70
    def
    -0.69
    PutMapping
    -0.69
    ynb
    -0.69
    void
    -0.69
    ///
    -0.68
    BufferException
    -0.68
     ngh
    -0.67
    POSITIVE LOGITS
     shore
    2.51
     swarovski
    2.17
     milf
    2.15
    Shore
    2.14
     excru
    2.14
     hairc
    2.13
     maneu
    2.12
     Shore
    2.11
     disagre
    2.05
     indestru
    2.05
    Activations Density 0.175%

    No Known Activations