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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2391
    Prev
    Next
    INDEX
    Explanations

    information related to web links, articles, and specific content

    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
    +0.15
    0.6%
    32
    +0.11
    0.4%
    919
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.15
    0.04
    32
    +0.11
    0.02
    281
    +0.08
    0.02
    Negative Logits
     intersper
    -1.50
    ⓧ
    -1.43
    <?
    -1.38
    
    -1.27
    /**
    -1.26
     endow
    -1.17
     quitted
    -1.10
     endeavored
    -1.09
     gratify
    -1.07
     plundered
    -1.05
    POSITIVE LOGITS
    =
    1.65
     =
    1.26
    }=
    1.25
    $=
    1.22
    )=
    1.22
    )]=
    1.21
    ))=
    1.21
    ]=
    1.21
    }}=
    1.19
    )}=
    1.19
    Activations Density 0.149%

    No Known Activations